Siemens Digital Industries Software’s SynthAI service is delivering the power of machine learning (ML) and artificial intelligence (AI) to solve the challenge of training machine vision systems.
“We were looking for a quick and easy solution that will enable us to detect wire terminals in a robotic electric cabinet assembly station. With SynthAI, our control engineers were able to achieve great results within just a few hours,” said Omer Einav, CEO of Siemens’ client, Polygon Technologies. “The tedious task of annotating a large set of training images to train the model was shortened significantly. The results show great promise for many additional use-cases we plan to handle with SynthAI.”
Machine learning is used for a variety of vision-based automation use-cases such as robotic bin picking, sorting, palletising, quality inspection and more. While usage of machine learning for vision-based automation is growing, many industries face challenges and struggle to implement it within their computer vision applications. This is due to the need to collect many images of the parts in question and the challenges associated with accurately annotating the different products within those images – particularly before production or manufacturing begins.
To solve this challenge, synthetic data is used to speed up the data collection and training process. However, utilising synthetic data for vision use-cases requires expertise in synthetic image generation and can be complex, time consuming and expensive. This is where Siemens’ SynthAI changes the game.
Rather than waiting for pre-production parts to be ready or using complex processes to generate synthetic data, machine vision specialists only need to provide 3D CAD data of the parts. SynthAI will then automatically generate thousands of randomised annotated synthetic images within minutes, without the specialist knowledge typically required.
SynthAI will also automatically train a machine learning model that could be used to detect a product in real life. Once the training is done, the trained model can be downloaded, tested and deployed offline, using no more than a little Python coding. If organisations prefer to handle training of their own systems, complete synthetic image datasets together with the annotations are also available.
Why choose between Capex and Opex if you can Totex? Schneider Electric South Africa
IT in Manufacturing
In a sector marked by cyclical demand, high capital intensity, and increasing regulatory and sustainability pressures, mining, minerals and metals (MMM) companies are re-evaluating how they approach procurement and investment.
Read more...AI and the smart factory Schneider Electric South Africa
IT in Manufacturing
Imagine walking into a factory where machines can think ahead, predict problems before they happen and automatically make adjustments to realise peak performance. This isn’t science fiction, it’s happening right now as AI continues to transform how we run industrial operations.
Read more...Why your supply chain should be a competitive advantage Schneider Electric South Africa
IT in Manufacturing
The last five years have placed unprecedented strain on global supply chains. Leading companies are turning the challenge into an opportunity to transform their supply chains into a competitive advantage.
Read more...Why AI will never truly understand machines Wearcheck
IT in Manufacturing
Cutting-edge technology and solutions powered by AI are embraced by specialist condition monitoring company, WearCheck, where the extreme accuracy of data used to assess and diagnose machine health is paramount.
Read more...Buildings and microgrids for a greener future Schneider Electric South Africa
IT in Manufacturing
Buildings are no longer passive consumers of power. Structures of almost every size are evolving into dynamic energy ecosystems capable of generating, storing and distributing their own electricity. Forming part of this exciting transformation are microgrids.
Read more...Traditional data centres are not fit for purpose
IT in Manufacturing
Traditional data centre designs are falling short, with nearly half of IT leaders admitting their current infrastructure does not support energy or carbon-reduction goals. New research commissioned by Lenovo reveals that data centre design must evolve to future-proof businesses.
Read more...AI agents for digital environment management in SA
IT in Manufacturing
The conversation about artificial intelligence in South Africa has shifted rapidly over the past year. Among the technologies changing the pace of business are AI agents - autonomous, task-driven systems designed to operate with limited human input.
Read more...AI-powered maintenance in future-ready data centres Schneider Electric South Africa
IT in Manufacturing
The data centre marketplace often still relies on outdated maintenance methods to manage mission-critical equipment. Condition-Based Maintenance (CBM) is powered by AI and is fast becoming a necessity in ensuring both competitiveness and resilience.
Read more...Powering up data centre mega development
IT in Manufacturing
Parker Hannifin has secured a major contract to supply key equipment for nearly 30 aeroderivative gas turbines powering a new hyperscale data centre in Texas.
Read more...Building resilient supply chains through smarter e-procurement RS South Africa
IT in Manufacturing
In a time of constant disruption, from supply chain uncertainty to rising operational costs, businesses that embrace digital procurement are better positioned to stay competitive and resilient.
While every effort has been made to ensure the accuracy of the information contained herein, the publisher and its agents cannot be held responsible for any errors contained, or any loss incurred as a result. Articles published do not necessarily reflect the views of the publishers. The editor reserves the right to alter or cut copy. Articles submitted are deemed to have been cleared for publication. Advertisements and company contact details are published as provided by the advertiser. Technews Publishing (Pty) Ltd cannot be held responsible for the accuracy or veracity of supplied material.
printer friendly version